|
|
|
A Wavelet Based Neural Network for DGPS Corrections Prediction
Dr. M. R. Mosavi
Behshahr University of Science and Technology
M_Mosavi@iust.ac.ir
Abstract
Neural Networks (NNs) are capable of learning high complex, nonlinear input-output mappings. This characteristic of NNs enables them to be used in nonlinear system modeling and prediction applications. On the other hand, the wavelet decomposition provides a powerful tool for functional approximation. In this paper, a kind of Wavelet Neural Networks (WNNs) is proposed for Differential GPS (DGPS) corrections prediction. The performance of proposed WNN is compared with Multilayer Perceptron (MLP) in the application of prediction. The proposed algorithms in DGPS system is implemented by a low cost commercial Coarse/Acquisition (C/A) code GPS module. The experimental results demonstrate which WNN has great approximation ability and suitability in prediction than MLP. So, position components RMS errors are less than 0.4 meter after of WNNs prediction.
|
|
|